Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

The "proper" binormal model: parametric receiver operating characteristic curve estimation with degenerate data

X Pan1, C E Metz

  • 1Department of Radiology, University of Chicago, IL, USA.

Academic Radiology
|May 1, 1997
PubMed
Summary

A new proper binormal model and PROPROC algorithm effectively fit receiver operating characteristic (ROC) curves from degenerate data, offering improved accuracy and robustness over conventional methods.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Precision CP Symmetry Test and Polarization Analysis in Σ^{+} Decays.

Physical review letters·2025
Same author

Precise Measurement of the Form Factors in D^{0}→K^{*}(892)^{-}μ^{+}ν_{μ}, and Test of Lepton Universality with D^{0}→K^{*}(892)^{-}ℓ^{+}ν_{ℓ} Decays.

Physical review letters·2025
Same author

sFlt-1/PlGF ratio thresholds for diagnosing pre-eclampsia in pregnant women with high blood pressure.

Ultrasound in obstetrics & gynecology : the official journal of the International Society of Ultrasound in Obstetrics and Gynecology·2025
Same author

First Measurement of the Decay Dynamics in the Semileptonic Transition of D^{+(0)} into the Axial-Vector Meson K[over ¯]_{1}(1270).

Physical review letters·2025
Same author

Observation of Three Resonant Structures in the Cross Section of e^{+}e^{-}→π^{+}π^{-}h_{c}.

Physical review letters·2025
Same author

Precision Measurement of the Branching Fraction of D^{+}→μ^{+}ν_{μ}.

Physical review letters·2025

Area of Science:

  • Biostatistics
  • Medical Imaging Analysis
  • Machine Learning in Healthcare

Background:

  • Receiver Operating Characteristic (ROC) curve analysis is crucial for evaluating diagnostic test performance.
  • Conventional binormal models can struggle with degenerate data, leading to inaccurate curve fitting.
  • Degenerate data presents challenges in estimating the true performance of diagnostic systems.

Purpose of the Study:

  • To assess a novel
  • proper
  • binormal model for Receiver Operating Characteristic (ROC) curve analysis.
  • To introduce and evaluate a new maximum-likelihood estimation algorithm for fitting ROC curves from degenerate data.

Main Methods:

  • The "proper" binormal ROC model utilizes a monotonic transformation of the likelihood ratio, ensuring monotonic slope.

Related Experiment Videos

  • A dedicated computer program, PROPROC, was developed and employed for fitting ROC curves.
  • The model and algorithm were tested using both computer-simulated and real observer study data.

    • Main Results:

    • The PROPROC program successfully fitted proper ROC curves to the datasets.
    • Estimates of ROC indexes, including total area, were computed using PROPROC.
    • Comparisons were made between PROPROC estimates and those from conventional binormal procedures.

    Conclusions:

    • The "proper" binormal ROC model effectively addresses the issue of degeneracy in ROC curve fitting.
    • The PROPROC algorithm demonstrates high robustness in ROC analysis.
    • PROPROC yields ROC estimates with reduced bias and enhanced precision compared to conventional methods.